How to use code-world-model/llama7b_math_pot_trace with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="code-world-model/llama7b_math_pot_trace")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("code-world-model/llama7b_math_pot_trace") model = AutoModel.from_pretrained("code-world-model/llama7b_math_pot_trace", device_map="auto")
https://huggingface.co/code-world-model/llama7b_math_pot_trace/resolve/main/tokenizer.json
hf download hf://code-world-model/llama7b_math_pot_trace/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/code-world-model/llama7b_math_pot_trace/resolve/main/tokenizer.json
